AI agents call getMyPlaylists to retrieve information from Yt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval only—it fetches the user's playlist information without creating, modifying, or deleting any content. While it accesses potentially sensitive data (private playlists), the read-only nature keeps it in the low-severity Read category. The OAuth requirement ensures access is authenticated and limited to the user's own data, further reducing risk.
From the tool's definition Tool name and description: 'Retrieves your own playlists from YouTube, including private playlists.' The verb 'retrieves' and explicit description of querying/fetching user data with no modification capability indicates a read-only operation.
Attacks that exploit this kind of access
Retrieves your own playlists from YouTube, including private playlists. Requires OAuth authentication. Use this to get detailed information about your personal playlists. It is categorised as a Read tool in the Yt MCP Server, which means it retrieves data without modifying state.
Register the Yt MCP server in PolicyLayer and add a rule for getMyPlaylists: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yt. Nothing to install.
getMyPlaylists is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the getMyPlaylists rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for getMyPlaylists. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
getMyPlaylists is provided by the Yt MCP server (yt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →